Python for Deep Learning: Build Neural Networks in Python

Name: Python for Deep Learning: Build Neural Networks in Python
Rating: 4.1 (1336 reviews)

Complete Deep Learning Course to Master Data science, Tensorflow, Artificial Intelligence, and Neural Networks

Created byMeta Brains, Skool of AI

Last updated 1/2024

English

What you'll learn

Learn the fundamentals of the Deep Learning theory
Learn how to use Deep Learning in Python
Learn how to use different frameworks in Python to solve real-world problems using deep learning and artificial intelligence
Make predictions using linear regression, polynomial regression, and multivariate regression
Build artificial neural networks with Tensorflow and Keras

Course content

11 sections • 59 lectures • 2h 4m total length

What is a Deep Learning ?3:13
Demystify deep learning by situating it within artificial intelligence and machine learning, explaining data-driven rules and neural networks as the core algorithmic approach.
Course Materials0:05
Why is Deep Learning Important?1:48
Software and Frameworks0:55

Single layer perceptron (SLP) model1:07
Radial Basis Network (RBN)0:56
Multi-layer perceptron (MLP) Neural Network0:54
Recurrent neural network (RNN)1:20
Long Short-Term Memory (LSTM) networks1:33
Hopfield neural network1:10
Explore the Hopfield neural network, a fully interconnected recurrent network with equal numbers of neurons, trained by setting neuron values to desired patterns and computing weights via deep learning algorithms.
Boltzmann Machine Neural Network0:56
Explore the Boltzmann machine neural network, a recurrent network with neurons connected to inputs, others not, using initialized weights learned via back propagation to yield binary judgments predisposed by biases.

Introduction0:45
Exploring the dataset1:19
Problem Statement0:44
Analyze bank customer behavior using independent variables to determine if customers leave or stay, and build a predictive model from data set to predict whether new customers stay or leave.
Data Pre-processing3:44
Loading the dataset1:48
Splitting the dataset into independent and dependent variables3:16
Split the dataset into independent variable X from column 3:13 and dependent variable Y from column 13 using iloc, then print X and Y to verify the split.
Label encoding using scikit-learn4:48
Transform gender and geography attributes into numeric form using label encoding and one hot encoding with scikit-learn pre-processing, enabling robust numeric input for deep learning models.
One-hot encoding using scikit-learn6:28
Learn to implement one-hot encoding in Python using scikit-learn's column transformer and one-hot encoder, transforming categorical geography data into numerical features for neural networks.
Training and Test Sets: Splitting Data3:51
Feature scaling3:54
Building the Artificial Neural Network2:06
Adding the input layer and the first hidden layer3:09
Add a dense layer to the classifier with six units and 11 input features, using a uniform weight initializer and relu activation to form the first hidden layer.
Adding the next hidden layer1:21
Adding the output layer1:35
Add the output layer with a single dense unit and sigmoid activation to predict a binary outcome, providing the probability of a customer leaving or staying.
Compiling the artificial neural network2:41
Fitting the ANN model to the training set2:15
Predicting the test set results4:29

Introduction3:54
Explore convolutional neural networks (CNNs) for image analysis, learn how large data and computing power revived CNNs in 2012, and how image normalization scales pixels from zero to one.
Components of convolutional neural networks1:07
Explore the two-step workflow of convolutional neural networks: feature extraction with filters and activation, then classification. Observe a convolutional neural network layout with input layer, pooling, and fully connected layers.
Convolution Layer3:16
Pooling Layer1:50
Fully connected Layer1:44

Requirements

Experience with the basics of coding in Python
Basic mathematical skills
Readiness, flexibility, and passion for learning

Description

Python is famed as one of the best programming languages for its flexibility. It works in almost all fields, from web development to developing financial applications. However, it's no secret that Python’s best application is in deep learning and artificial intelligence tasks.

While Python makes deep learning easy, it will still be quite frustrating for someone with no knowledge of how machine learning works in the first place.

If you know the basics of Python and you have a drive for deep learning, this course is designed for you. This course will help you learn how to create programs that take data input and automate feature extraction, simplifying real-world tasks for humans.

There are hundreds of machine learning resources available on the internet. However, you're at risk of learning unnecessary lessons if you don't filter what you learn. While creating this course, we've helped with filtering to isolate the essential basics you'll need in your deep learning journey.

It is a fundamentals course that’s great for both beginners and experts alike. If you’re on the lookout for a course that starts from the basics and works up to the advanced topics, this is the best course for you.

It only teaches what you need to get started in deep learning with no fluff. While this helps to keep the course pretty concise, it’s about everything you need to get started with the topic.

Who this course is for:

Programmers who are looking to add deep learning to their skillset
Professional mathematicians willing to learn how to analyze data programmatically
Any Python programming enthusiast willing to add deep learning proficiency to their portfolio

Python for Deep Learning: Build Neural Networks in Python

What you'll learn

Explore related topics

Course content

Introduction to Deep Learning4 lectures • 6min

Artificial Neural Networks (ANN)4 lectures • 8min

Propagation of information in ANNs3 lectures • 4min

Neural Network Architectures7 lectures • 8min

Activation Functions7 lectures • 10min

Gradient Descent Algorithm3 lectures • 5min

Summary Overview of Neural Networks4 lectures • 7min

Implementation of ANN in Python17 lectures • 48min

Convolutional Neural Networks (CNN)5 lectures • 12min

Implementation of CNN in Python4 lectures • 17min

Requirements

Description

Who this course is for: